Integrating sensor streams for robotic demonstration learning

US11534913B2 · kind B2 · utility

Assignee

• Intrinsic Innovation LLC · US

Inventors

• Bala Venkata Sai Ravi Krishna Kolluri · Fremont, US
• Stefan Schaal · Mountain View, US
• Ralf Oliver Michael Schönherr · San Francisco, US
• Benjamin Davis · Oakland, US
• Ning Ye · San Jose, US

Key dates

• Filing date: May 21, 2020
• Grant date: Dec 27, 2022
• Expiry date: Feb 16, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G05B2219/42263
• WIPO field: Handling
• WIPO sector: Mechanical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for integrating sensor streams for robotic demonstration learning. One of the methods includes selecting, by a learning system for a robot, a base update rate for combining multiple sensor streams into a task state representation. The learning system repeatedly generates the task state representation at the base update rate, including combining, during each time period defined by the update rate, the task state representation from most recently updated sensor data processed by the plurality of neural networks. The learning system repeatedly uses the task state representations to generate commands for the robot at the base update rate.